Index of every page on this site: llms.txt
All skills
tristanmanchester avatar

/meta-ads-cli

@3323bc9
by Tristan Manchestertristanmanchester/agent-skills3 stars
2
Run it yourself

Inspect, report on, and deliberately manage Meta Facebook/Instagram advertising through Meta's official Ads CLI. Use for the user's ad accounts, campaigns, ad sets, creatives, delivery, budgets, datasets, and catalogues; not for general social posting or automatic ad optimisation.

Use this Skill: https://skilld.dev/gh/tristanmanchester/agent-skills/meta-ads-cli

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

README.md

≈328 tokens on demand. Your agent reads this file only when SKILL.md points to it.

meta-ads-cli

A provider-specific Agent Skill for Meta's official meta-ads package. Start with SKILL.md.

The official CLI handles routine account, campaign, ad set, ad, creative, catalogue, dataset, and Insights operations. The small scripts/meta_graph.py fallback retains raw Graph calls, independent batches, and image/video uploads when installed CLI help confirms a gap. It does not duplicate the full CRUD client.

Revision 3 removes the heuristic command-risk wrapper, automatic plan runner, duplicate agent prompts, and stale command/risk catalogues. They were not a reliable authorisation boundary. The direct workflow requires specific user authorisation, paused creation, exact account context, and read-after-write verification.

The fallback accepts only relative paths on https://graph.facebook.com, never follows redirects or paging URLs, performs no automatic retry, and reports per-item batch failure. Writes require an exact locally reviewed plan hash. Existing scripts and environment conventions from meta-ads-control are not compatibility interfaces.

This skill's MIT licence does not relicense Meta's proprietary CLI. Offline tests use synthetic data and mocks, not an ad account. No live CLI/API compatibility or advertising result is implied by those tests.

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

1 warning1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    This skill provides a structured framework for managing Meta Ads via a CLI safety wrapper. It includes a Python guard script designed to prevent accidental high-spend operations and credential leaks. The skill processes external campaign data which presents a minor risk for indirect prompt injection, and there is a discrepancy in the metadata regarding the skill's author.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: MEDIUM · 1 issue

Provenance

Signed by skilld at 3323bc9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Steadyupdated last month

Capability

metadata
{
  "version": "3.0.0",
  "reviewed": "2026-09-13"
}
Other metadata
compatibility
A shell and Meta's official meta-ads package on a supported Python 3.12+ platform. ACCESS_TOKEN and AD_ACCOUNT_ID provide account context. The optional Graph fallback needs Python 3.10+ and an explicitly selected supported API version.

README badge

README badge for tristanmanchester/agent-skills/meta-ads-cli